# Exploring the Capability of LLMs in Performing Low-Level Visual Analytic Tasks on SVG Data Visualizations

arXiv: https://arxiv.org/abs/2404.19097 · HTML: https://mlsanity.com/paper/2404.19097/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2024.

## Built on by (most cited first, 18 of 18)

- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation](https://mlsanity.com/paper/2506.03139/) (2025)
- [GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs](https://mlsanity.com/paper/2505.17653/) (2025)
- [EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts](https://mlsanity.com/paper/2508.04650/) (2025)
- [ParaView-MCP: An Autonomous Visualization Agent with Direct Tool Use](https://mlsanity.com/paper/2505.07064/) (2025)
- [Visualization Literacy of Multimodal Large Language Models: A Comparative Study](https://mlsanity.com/paper/2407.10996/) (2024)
- [ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset](https://mlsanity.com/paper/2501.09349/) (2025)
- [See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMs](https://mlsanity.com/paper/2504.09809/) (2025)
- [MapIQ: Evaluating Multimodal Large Language Models for Map Question Answering](https://mlsanity.com/paper/2507.11625/) (2025)
- [Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review](https://mlsanity.com/paper/2503.04983/) (2025)
- [Does visualization help AI understand data?](https://mlsanity.com/paper/2507.18022/) (2025)
- [Do Language Model Agents Align with Humans in Rating Visualizations? An Empirical Study](https://mlsanity.com/paper/2505.06702/) (2025)
- [LangLasso: Interactive Cluster Descriptions through LLM Explanation](https://mlsanity.com/paper/2601.10458/) (2026)
- [A Deep User Interface for Exploring LLaMa](https://mlsanity.com/paper/2502.20938/) (2025)
- [Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks](https://mlsanity.com/paper/2510.06071/) (2025)
- [SVG Decomposition for Enhancing Large Multimodal Models Visualization Comprehension: A Study with Floor Plans](https://mlsanity.com/paper/2511.03478/) (2025)
- [MM-SVGEdit: A Multimodal-Driven SVG Editing for UI Design](https://mlsanity.com/paper/2609.06116/) (2026)
- [WidgetVA: A Widget-Centric Framework and Benchmark for Agentic Visual Analytics](https://mlsanity.com/paper/2609.24094/) (2026)

## Abstract (arXiv)

Data visualizations help extract insights from datasets, but reaching these insights requires decomposing high level goals into low-level analytic tasks that can be complex due to varying degrees of data literacy and visualization experience. Recent advancements in large language models (LLMs) have shown promise for lowering barriers for users to achieve tasks such as writing code and may likewise facilitate visualization insight. Scalable Vector Graphics (SVG), a text-based image format common in data visualizations, matches well with the text sequence processing of transformer-based LLMs. In this paper, we explore the capability of LLMs to perform 10 low-level visual analytic tasks defined by Amar, Eagan, and Stasko directly on SVG-based visualizations. Using zero-shot prompts, we instruct the models to provide responses or modify the SVG code based on given visualizations. Our findings demonstrate that LLMs can effectively modify existing SVG visualizations for some tasks like Cluster but perform poorly on tasks requiring mathematical operations like Compute Derived Value. We also discovered that LLM performance can vary based on factors such as the number of data points, the presence of value labels, and the chart type. Our findings contribute to gauging the general capabilities of LLMs and highlight the need for further exploration and development to fully harness their potential in supporting visual analytic tasks.